Unlike traditional identity theft, SIF blends real and fabricated information to create convincing yet fictitious profiles that are difficult to detect.
Mr. Borketey, a recognized expert in data science and fraud detection, proposes a groundbreaking approach to tackling this issue. By combining the Social Security Administration’s (SSA) Electronic Consent-Based Social Security Number Verification (eCBSV) system with machine learning models such as those discovered in his recent publication titled “Real-Time Fraud Detection Using Machine Learning”, Mr. Borketey outlines a vision for a robust and adaptable framework that could transform how financial institutions detect and prevent SIF.
Understanding the Problem: The Threat of Synthetic IDs
Synthetic identity fraud involves creating a fictitious identity using a real Social Security Number (SSN) combined with fabricated personal details such as names and addresses. Fraudsters often use SSNs belonging to minors, deceased individuals, or those with no credit history, enabling these identities to pass standard Know Your Customer (KYC) checks. Over time, these synthetic identities can establish credit histories, making them even harder to detect.
“Synthetic IDs can blend seamlessly into our systems,” explains Mr. Borketey. “They mimic legitimate customer behavior, exploiting the gaps in traditional fraud detection methods.”
This type of fraud poses significant risks, not only to financial institutions but also to vulnerable populations whose SSNs are unknowingly used in fraudulent schemes. Existing tools often fall short in identifying the subtle patterns that distinguish synthetic identities from real ones.
A Proposed Solution: Fusing eCBSV with Machine Learning
Recognizing the limitations of current fraud detection methods, Mr. Borketey proposes a novel approach that combines eCBSV and machine learning. The eCBSV system provides a reliable foundation for identity verification by confirming whether an SSN, name, and date of birth combination matches SSA records. However, as Mr. Borketey highlights, eCBSV alone cannot address the behavioral and systemic complexities of synthetic fraud.
“Machine learning complements eCBSV by identifying patterns and behaviors that are indicative of fraud,” says Mr. Borketey. “This fusion of technologies offers a comprehensive strategy for detecting synthetic identities.”
By leveraging the strengths of both eCBSV and machine learning, financial institutions could develop a multi-layered approach to fraud detection that adapts to evolving tactics. Machine learning models can analyze behavioral data, credit histories, and application patterns, providing deeper insights that traditional tools miss.
Applications of the Proposed Framework
Mr. Borketey’s proposed framework has wide-ranging applications across financial products, including:
- Credit Card Applications: Machine learning can identify suspicious profiles that eCBSV alone might miss, such as new SSNs with rapid credit growth or unusual application patterns.
- Loan Requests: By combining eCBSV validation with behavioral analysis, institutions can flag anomalies like large loan requests from newly established credit profiles.
- Account Openings: The system could detect irregularities such as repeated use of the same address across multiple accounts.
- Credit Limit Increases: Fraudsters often use synthetic identities to request credit limit increases. Machine learning models can spot patterns that indicate potential fraud.
- Authorized User Additions: Synthetic identities attempting to exploit authorized user loopholes could be flagged based on repetitive or unusual behaviors.
Benefits of the Proposed Approach
Mr. Borketey’s proposal offers significant benefits to financial institutions and consumers. The combination of eCBSV and machine learning not only enhances fraud detection accuracy but also provides a scalable solution that evolves alongside emerging threats. Additionally, this approach helps protect vulnerable groups—such as minors and the elderly—whose SSNs are often exploited in synthetic fraud schemes.
“Fraud detection must be proactive and dynamic,” says Mr. Borketey. “The tools we use today should anticipate the challenges of tomorrow.”
A Call to Action
As synthetic identity fraud continues to grow, Mr. Borketey emphasizes the need for industry-wide collaboration to implement advanced fraud detection systems. He calls on financial institutions, regulators, and technology providers to explore the fusion of eCBSV and machine learning, ensuring a safer and more resilient financial ecosystem.
About Mr. Borketey
Borketey’s expertise spans fraud detection, data science, data management, prediction, forecasting, Machine Learning, and Artificial Intelligence. With 7 years of experience in the U.S. financial sector, he specializes as a Data Scientist, focusing on developing advanced machine learning models for fraud detection. He has also authored multiple publications on machine learning and has spoken at numerous conferences. He holds a master’s degree in Quantitative Economics and Econometrics from the University of Akron in Ohio. Additionally, he possesses a postgraduate certificate in Machine Learning and Artificial Intelligence from Purdue University.
Copyright © 2024 California Business Journal. All Rights Reserved.
For California Business Journal Disclaimers, go to https://calbizjournal.com/terms-conditions/.
